A Speech Preprocessing Method Based on Perceptually Optimized Envelope Processing to Increase Intelligibility in Reverberant Environments

Speech intelligibility in public places can be degraded by the environmental noise and reverberation. In this study, a new near-end listening enhancement (NELE) approach is proposed which using time varying filter jointly enhances onsets reduces overlap masking. For optimization, some look-ahead clean speech prior knowledge of room impulse response (RIR) are required. method, optimizing defined cost function, Spectro-Temporal Envelope reverb optimized to as close possible that speech. with increased weight. This different from overlap-masking ratio (OMR) (OE) approaches (Grosse, van de Par, 2017, J. Audio Eng. Soc., Vol. 65 (1/2), pp. 31–41) only consider previous frames each slot for determining variant filtering. The SRT measurements show optimization framework up 2 dB more OE.